Neural Math Word Problem Solver with Reinforcement Learning

By Danqing Huang, Jing Liu, Chin-Yew Lin, Jian Yin. 2018

91 citations recorded by the source corpus.

Subfields: Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

Training Verifiers to Solve Math Word Problems (2021, background): “Previous work has attempted to solve classic math word problem benchmarks with recurrent seq2seq models (Sutskever et al., 2014) and closely related variants (Wang et al., 2017; Huang et al., 2018).”
MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms (2019, methodology): “…features introduced by prior work are arguably “interpretable” due to the relative sparsity of features as well as the clear alignments between inputs and outputs, new neuralized approaches present new challenges to model interpretability of math word problem solvers (Huang et al., 2018a).”
Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction (2022, methodology): “Other approaches improve the seq2seq model with reinforcement learning (Huang et al., 2018), template-based methods (Wang et al., 2019), and group attention mechanism (Li et al., 2019).”
Modeling Intra-Relation in Math Word Problems with Different Functional Multi-Head Attentions (2019, background): “In recent years, a growing number of deep learning models for MWPs (Wang et al., 2017; Ling et al., 2017; Wang et al., 2018b,a; Huang et al., 2018a,b; Wang et al., 2019) have drawn inspiration from advances in machine translation.”
An Overview of Natural Language State Representation for Reinforcement Learning (2020, background): “…in LSTMs) was set as the environment state in language modeling (Ranzato et al., 2015), image captioning (Rennie et al., 2017), math word problem (Huang et al., 2018) and NLG (Yasui et al., 2019), sometimes with attention over hidden states of a sequence in grammatical error correction…”
Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks (2021, background): “Recently, many researchers (Wang et al., 2017; Huang et al., 2018; Wang et al., 2018b, 2019; Xie and Sun, 2019; Chiang and Chen, 2019), inspired by an encoder-decoder framework (Cho et al., 2014), apply neural networks to solve MWPs by learning the mapping function between problems and their…”
A Bottom-Up DAG Structure Extraction Model for Math Word Problems (2021, background): “Thus, Huang et al. (2018) incorporated copy and alignment mechanisms to alleviate this problem.”
HMS: A Hierarchical Solver with Dependency-Enhanced Understanding for Math Word Problem (2021, methodology): “With the advantages of automatic feature extraction and strong generality, deep learning methods especially seq2seq models have been widely used in recent studies (Wang, Liu, and Shi 2017; Huang et al. 2018; Wang et al. 2019; Xie and Sun 2019; Wang et al. 2018c; Zhang et al. 2020).”
Point to the Expression: Solving Algebraic Word Problems Using the Expression-Pointer Transformer Model (2020, methodology): “• Pure neural models take algebraic word problems as the raw input to a neural model and do not require the use of a rule-based model: CASS-RL (Huang et al., 2018) and T-MTDNN (Lee and Gweon, 2020).”
The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, methodology): “This is an emerging research direction for MWP solvers and we observed multiple instances, including Deep Neural Solver [14], Seq2SeqET [15], StackDecoder [16], MathDQN [17], CASS [18], T-RNN [19].”
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems (2021, unknown): “…1985; Bakman, 2007), statistical machine learning methods (Kushman et al., 2014; Hos-seini et al., 2014), semantic parsing methods (Shi et al., 2015; Koncel-Kedziorski et al., 2015) and deep learning methods (Wang et al., 2017; Huang et al., 2018a,b; Xie and Sun, 2019; Zhang et al., 2020).”
A Weakly Supervised Model for Solving Math word Problems (2021, methodology): “More recently, neural network-based MWP solving methods (Wang et al., 2017, 2018a,b; Huang et al., 2018; Chiang and Chen, 2019; Wang et al., 2019; Liu et al., 2019; Xie and Sun, 2019) have been proposed.”
A Survey of Deep Learning for Mathematical Reasoning (2022, unknown): “A large amount of work has shown the performance advantage of Seq2Seq models over previous statistical learning approaches (Ling et al., 2017; Wang et al., 2018a; Huang et al., 2018; Chiang and Chen, 2019; Wang et al., 2019; Li et al., 2019).”
Learning by Fixing: Solving Math Word Problems with Weak Supervision (2020, methodology): “2017) to recent deep learning methods (Ling et al. 2017; Wang, Liu, and Shi 2017; Huang et al. 2018; Robaidek, Koncel-Kedziorski, and Hajishirzi 2018; Wang et al. 2018, 2019; Chiang and Chen 2019; Xie and Sun 2019; Zhang et al. 2020a).”
Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems (2020, methodology): “Another way is that we can deploy Seq2Seq-based architecture to handle various equations in inﬁx order like in previous works (Wang et al., 2017; Huang et al., 2018), but there are some limitations, such as generating invalid expression, generating spurious numbers, and generating numbers at wrong…”